Miguel Bronchud, Co-Founder and Advisory Board at Regenerative Medicine Solutions, shared a post on LinkedIn:
“AI for patients selection in clinical oncology trials? Promising early results just presented at pioneering ESMO AI and Digital Oncology Congress 2025 (Berlin, 12–14 November)
Manual identification of patients for inclusion in clinical trials is laborious and some patients who are eligible can be overlooked in the process.
“Here is where artificial intelligence (AI) can play a central role,” observes Prof. Rudolf Fehrmann from the University Medical Center Groningen, Netherlands. “Preliminary data highlight an opportunity for AI to potentially improve patient selection and accrual in trials.”
Proof of concept comes from a study were very recently presented at the ESMO AI & Digital Oncology Congress 2025 (Berlin, 12–14 November) where an AI-powered platform(MedgicalAI®), leveraging a large language model (LLM), showed that automated eligibility matching of patients referred to a phase I drug development unit is feasible (Abstract 382MO).
In total, 108 patients were assessed and the LLM matching platform identified 41 true positives and 6 false positives, yielding 87% precision for the proportion of AI-generated matches that were truly eligible based on clinical validation.
The authors of this abstract (not yet published in paper format) reported high concordance of AI with the allocation decisions of clinical experts, discordances being due mainly to external constraints, such as trial slot availability and incomplete clinical referral data.
See also:
Silva DJDD, et al. Enhancing phase I clinical trial selection using artificial intelligence: Evaluation of a large language model algorithm in a dedicated drug development unit. ESMO AI & Digital Oncology Congress 2025 – Abstract 382MO
* N=108
* Large language model algorithm:
* Total patients allocated: 47
* True positives: 41
* False positives: 6
* Precision: 87%
* Recall: 100%
* F1 score: 93%
Or: Bois’s et al. Identification of a very low-risk subgroup in breast cancer using a combination of spatial representation and AI-derived prognostics
LLM platform demonstrated high concordance with expert multidisciplinary allocation decisions regarding patient eligibility for referral to a phase I drug development unit (ESMO AI & Digital Oncology Congress 2025, Abstract 382MO)
“Of course, these findings were observed in a limited set of data, conducted in the context of an experienced phase I clinical trial unit,” notes Fehrmann.
It will be interesting to see how this type of tool would cope with much larger databases involving the complex inclusion and exclusion criteria associated with later-phase III trials. Do “inclusion” and “exclusion” criteria induce clinical outcomes biased conclusions?
In addition, how will it perform outside the specialist setting, for example, in general clinical practice where there may be less comprehensive patient information provided?
Remembering that the degree of benefit AI can provide over manual selection remains to be assessed.”
More posts featuring Miguel Bronchud on OncoDaily.